This paper proposes a neural networks predistorter based on the bidirectional long-short-term memory (BiLSTM) structure. The proposed predistorter was trained while ensuring that it captures the full intrinsic behavior of the device under test including its memory effects and nonlinear distortions. For this purpose, the device under test was characterized while operating at peak power level with a test signal that emulates strong memory effects. Extensive experimental validation carried on a commercial Gallium Nitride power amplifier prototype demonstrated the ability of the proposed predistorter to maintain standard compliant adjacent channel leakage ratio over a wide range of operating conditions including operating average power, signal bandwidth, and carriers' configurations. It has been shown that a digital predistorter (DPD) derived from one single training condition was able to linearize the device under test for 72 different test conditions with signal bandwidths between 10MHz and 40MHz, and an operating power range of 5dB. Furthermore, benchmarking results showed that the BiLSTM DPD is unable to maintain satisfactory performance when trained with a sub-optimal signal which does not emulate the full behavior of the device under test. Moreover, it has been shown that the use of the optimal characterization signal along with a generalized memory polynomial predistorter does not lead to satisfactory performance. Hence, the resilience of the predistorter is obtained by combining the suitable model structure along with the appropriate training approach. Such resilient DPD presents a paradigm shift in predistortion techniques which significantly minimizes the need for update. It is anticipated that this work will pave the road for a new generation of DPDs resilient to a wide range of operating conditions.

The human nervous system is one of the most complex systems of the human body. Understanding its behavior is crucial in drug discovery and developing medical devices. One approach to understanding such a system is to model its most basic unit, neurons. The leaky integrate and fire (LIF) method models the neurons’ response to a stimulus. Given the fact that the model’s equation is a linear ordinary differential equation, the purpose of this research is to compare which numerical analysis method gives the best results for the simplified version of this model. Adams predictor and corrector (AB4-AM4) and Heun’s methods were then used to solve the equation. In addition, this study further researches the effects of different current input models on the LIF’s voltage output. In terms of the computational time, Heun’s method was 0.01191 s on average which is much less than that of the AB-AM4 method (0.057138) for a constant DC input. As for the root mean square error, the AB-AM4 method had a much lower value (0.0061) compared to that of Heun’s method (0.3272) for the same constant input. Therefore, our results show that Heun’s method is best suited for the simplified LIF model since it had the lowest computation time of 36 ms, was stable over a larger range, and had an accuracy of 72% for the varying sinusoidal current input model.